<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jinman-etal-2020-pbos">
    <titleInfo>
        <title>PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhao</namePart>
        <namePart type="family">Jinman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shawn</namePart>
        <namePart type="family">Zhong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaomin</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yingyu</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We look into the task of generalizing word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, without extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections and affix prediction experiment show that PBoS is able to produce meaningful subword segmentations and subword rankings without any source of explicit morphological knowledge. Word similarity and POS tagging experiments show clear advantages of PBoS over previous subword-level models in the quality of generated word embeddings across languages.</abstract>
    <identifier type="citekey">jinman-etal-2020-pbos</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.53</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.53</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>596</start>
            <end>611</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding
%A Jinman, Zhao
%A Zhong, Shawn
%A Zhang, Xiaomin
%A Liang, Yingyu
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jinman-etal-2020-pbos
%X We look into the task of generalizing word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, without extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections and affix prediction experiment show that PBoS is able to produce meaningful subword segmentations and subword rankings without any source of explicit morphological knowledge. Word similarity and POS tagging experiments show clear advantages of PBoS over previous subword-level models in the quality of generated word embeddings across languages.
%R 10.18653/v1/2020.findings-emnlp.53
%U https://aclanthology.org/2020.findings-emnlp.53
%U https://doi.org/10.18653/v1/2020.findings-emnlp.53
%P 596-611

Markdown (Informal)

[PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding](https://aclanthology.org/2020.findings-emnlp.53) (Jinman et al., Findings 2020)

• PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (Jinman et al., Findings 2020)

ACL

• Zhao Jinman, Shawn Zhong, Xiaomin Zhang, and Yingyu Liang. 2020. PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 596–611, Online. Association for Computational Linguistics.